Yikun Wang | Fudan University

About Me [CV]

Hi, I am a Ph.D. student in Fudan University & SII (Joint Program), currently supervised by Prof. Dacheng Tao. I conduct research on Multimodal LLMs and LLM agents. Previously, I worked with Dr. Xuanjing Huang, Dr. Fei Liu, and Dr. Yiran Chen from Duke CEI Lab on robust watermarking.

Please feel free to contact me for discussion and collaboration!

Publications [Google Scholar]

arXiv

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Dianyi Wang, Wei Song, Yikun Wang, Siyuan Wang, Kaicheng Yu, Zhongyu Wei, Jiaqi Wang

ArXiv Technical Report, 2025

PDF

arXiv

GeometryZero: Improving Geometry Solving for LLM with Group Contrastive Policy Optimization

Yikun Wang, Yibin Wang, Dianyi Wang, Zimian Peng, Qipeng Guo, Dacheng Tao, Jiaqi Wang

ArXiv Technical Report, 2025

PDF

ACL

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Yikun Wang*, Siyin Wang*, Qinyuan Cheng, Zhaoye Fei, Liang Ding, Qipeng Guo, Dacheng Tao, Xipeng Qiu

ACL, 2025 (Main)

PDF

ACL

Uncertainty Aware Learning for Language Model Alignment

Yikun Wang*, Rui Zheng*, Liang Ding, Qi Zhang, Dahua Lin, Dacheng Tao

ACL, 2024 (Main)

PDF

ACL

RRescue: Ranking LLM Responses to Enhance Reasoning Over Context

Yikun Wang*, Rui Zheng*, Haoming Li, Qi Zhang, Tao Gui, Fei Liu

ACL, 2024 (SRW)

PDF

arXiv

LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition

Junjie Ye, Nuo Xu, Yikun Wang, Jie Zhou, Qi Zhang, Tao Gui, Bingning Wang, Xuanjing Huang

ArXiv Technical Report

PDF

Industry Experience

Tencent Hunyuan, Shanghai, China

Hunyuan Research Intern

Topic: Frontier visual reasoning model; supervised finetuning and reinforcement learning

Jul. 2025 ~ Present

Shanghai Artificial Intelligence Lab, Shanghai, China

LLM Research Intern

Topic: LLM pretraining, reward modeling

Mar. 2024 ~ Sept. 2024